Upload app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import numpy as np
 import matplotlib.pyplot as plt
-import librosa
 
 HOME_DIR = ""
 local_config_path = 'config.json'
@@ -109,7 +108,7 @@ saved_model = torch.load(model_path, map_location=torch.device('cpu'))
 model = Wav2Vec2ForSpeechClassification(config=config)
 
 # Load the state dictionary
-model.load_state_dict(saved_model, strict=False)
+model.load_state_dict(saved_model)
 
 print("Model initialized successfully.")
 
@@ -117,10 +116,10 @@ model.eval()
 
 
 def recognize_emotion(audio):
+    import librosa
     # Load the audio file using librosa
-    #audio, _ = librosa.load(file_path, sr=16000) 
+
     sample_rate, audio_data = audio
-    print(audio_data)
 
      # Ensure audio data is in floating-point format
     if not np.issubdtype(audio_data.dtype, np.floating):